English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

In this paper, we describe an approach for modelling causal reasoning innatural language by detecting counterfactuals in text using multi-headself-attention weights. We use pre-trained transformer models to extractcontextual embeddings and self-attention weights from the text. We show the useof convolutional layers to extract task-specific features from theseself-attention weights. Further, we describe a fine-tuning approach with acommon base model for knowledge sharing between the two closely relatedsub-tasks for counterfactual detection. We analyze and compare the performanceof various transformer models in our experiments. Finally, we perform aqualitative analysis with the multi-head self-attention weights to interpretour models' dynamics.

CNRL at SemEval-2020 Task 5: Modelling Causal Reasoning in Language with Multi-Head Self-Attention Weights based Counterfactual Detection